{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3URZWC37CXINPDCJC52SQKJ6MY","short_pith_number":"pith:3URZWC37","schema_version":"1.0","canonical_sha256":"dd239b0b7f15d0d78c49177528293e661606d38825b5165de6960d21abee52e5","source":{"kind":"arxiv","id":"2607.08768","version":1},"attestation_state":"computed","paper":{"title":"UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bohao Li, Chengqi Duan, Kaiyue Sun, Manyuan Zhang, Xihui Liu, Yuqing Wang, Zhekai Chen","submitted_at":"2026-07-09T17:59:32Z","abstract_excerpt":"The rapid development of large language models and multimodal large language models has accelerated the emergence of proactive agents capable of operating everyday tools and assisting users in real-world environments. However, existing benchmarks struggle to evaluate such agents effectively, as they often rely on sandboxed environments and single-turn evaluation paradigms. Moreover, their scenario-based task taxonomies mix multiple model capabilities within the same task category, making it difficult to identify the root causes of agent failures. To address these limitations, we introduce UniC"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.08768","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-09T17:59:32Z","cross_cats_sorted":[],"title_canon_sha256":"42fcca74432c744f0c4135fe64e4f00791e7323259789ab293d03368023dede9","abstract_canon_sha256":"48f8c1460856cbe77c13bcae9fe14d6f6d6bcd22e409afe67559c9cd46587daf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T01:19:59.761463Z","signature_b64":"FvjzH3NXXFTTSeJJbEiB9RqDexrdUb2atP9dvbi71TaiqooqhluXY8JsOUZIOhGZEJ1CJMRSDrAMBSUp2X+hDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd239b0b7f15d0d78c49177528293e661606d38825b5165de6960d21abee52e5","last_reissued_at":"2026-07-10T01:19:59.760829Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T01:19:59.760829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bohao Li, Chengqi Duan, Kaiyue Sun, Manyuan Zhang, Xihui Liu, Yuqing Wang, Zhekai Chen","submitted_at":"2026-07-09T17:59:32Z","abstract_excerpt":"The rapid development of large language models and multimodal large language models has accelerated the emergence of proactive agents capable of operating everyday tools and assisting users in real-world environments. However, existing benchmarks struggle to evaluate such agents effectively, as they often rely on sandboxed environments and single-turn evaluation paradigms. Moreover, their scenario-based task taxonomies mix multiple model capabilities within the same task category, making it difficult to identify the root causes of agent failures. To address these limitations, we introduce UniC"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08768","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.08768/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.08768","created_at":"2026-07-10T01:19:59.761036+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.08768v1","created_at":"2026-07-10T01:19:59.761036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08768","created_at":"2026-07-10T01:19:59.761036+00:00"},{"alias_kind":"pith_short_12","alias_value":"3URZWC37CXIN","created_at":"2026-07-10T01:19:59.761036+00:00"},{"alias_kind":"pith_short_16","alias_value":"3URZWC37CXINPDCJ","created_at":"2026-07-10T01:19:59.761036+00:00"},{"alias_kind":"pith_short_8","alias_value":"3URZWC37","created_at":"2026-07-10T01:19:59.761036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.10875","citing_title":"VibeLifeBench: Can Your Life Agent Be Proactive and Persistent in a Living World?","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3URZWC37CXINPDCJC52SQKJ6MY","json":"https://pith.science/pith/3URZWC37CXINPDCJC52SQKJ6MY.json","graph_json":"https://pith.science/api/pith-number/3URZWC37CXINPDCJC52SQKJ6MY/graph.json","events_json":"https://pith.science/api/pith-number/3URZWC37CXINPDCJC52SQKJ6MY/events.json","paper":"https://pith.science/paper/3URZWC37"},"agent_actions":{"view_html":"https://pith.science/pith/3URZWC37CXINPDCJC52SQKJ6MY","download_json":"https://pith.science/pith/3URZWC37CXINPDCJC52SQKJ6MY.json","view_paper":"https://pith.science/paper/3URZWC37","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.08768&json=true","fetch_graph":"https://pith.science/api/pith-number/3URZWC37CXINPDCJC52SQKJ6MY/graph.json","fetch_events":"https://pith.science/api/pith-number/3URZWC37CXINPDCJC52SQKJ6MY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3URZWC37CXINPDCJC52SQKJ6MY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3URZWC37CXINPDCJC52SQKJ6MY/action/storage_attestation","attest_author":"https://pith.science/pith/3URZWC37CXINPDCJC52SQKJ6MY/action/author_attestation","sign_citation":"https://pith.science/pith/3URZWC37CXINPDCJC52SQKJ6MY/action/citation_signature","submit_replication":"https://pith.science/pith/3URZWC37CXINPDCJC52SQKJ6MY/action/replication_record"}},"created_at":"2026-07-10T01:19:59.761036+00:00","updated_at":"2026-07-10T01:19:59.761036+00:00"}